Model: GPT-2 Xl: 48 Layers, 6400 Neurons per Layer
Dataset: Open Web Text
Neuron 2039 in Layer 45
Transformer Lens Loading: HookedTransformer.from_pretrained('gpt2-xl')
Text #0
Max Range: 7.3892. Min Range: -7.3892
Max Act: 7.3892. Min Act: -0.1700
Data Index: 1196313 (Open Web Text)
Max Activating Token Index: 769
Click toggle to see full text
Truncated
Full Text #0
Text #1
Max Range: 7.3892. Min Range: -7.3892
Max Act: 7.2642. Min Act: -0.1700
Data Index: 4888120 (Open Web Text)
Max Activating Token Index: 211
Click toggle to see full text
Truncated
Full Text #1
Text #2
Max Range: 7.3892. Min Range: -7.3892
Max Act: 7.2017. Min Act: -0.1700
Data Index: 6374345 (Open Web Text)
Max Activating Token Index: 232
Click toggle to see full text
Truncated
Full Text #2
Text #3
Max Range: 7.3892. Min Range: -7.3892
Max Act: 7.2017. Min Act: -0.1700
Data Index: 1793198 (Open Web Text)
Max Activating Token Index: 964
Click toggle to see full text
Truncated
Full Text #3
Text #4
Max Range: 7.3892. Min Range: -7.3892
Max Act: 7.2017. Min Act: -0.1700
Data Index: 4536118 (Open Web Text)
Max Activating Token Index: 764
Click toggle to see full text
Truncated
Full Text #4
Text #5
Max Range: 7.3892. Min Range: -7.3892
Max Act: 7.0142. Min Act: -0.1700
Data Index: 4852053 (Open Web Text)
Max Activating Token Index: 612
Click toggle to see full text
Truncated
Full Text #5
Text #6
Max Range: 7.3892. Min Range: -7.3892
Max Act: 6.9517. Min Act: -0.1700
Data Index: 6750791 (Open Web Text)
Max Activating Token Index: 386
Click toggle to see full text
Truncated
Full Text #6
Text #7
Max Range: 7.3892. Min Range: -7.3892
Max Act: 6.9204. Min Act: -0.1700
Data Index: 815077 (Open Web Text)
Max Activating Token Index: 421
Click toggle to see full text
Truncated
Full Text #7
Text #8
Max Range: 7.3892. Min Range: -7.3892
Max Act: 6.8892. Min Act: -0.1700
Data Index: 5334433 (Open Web Text)
Max Activating Token Index: 351
Click toggle to see full text
Truncated
Full Text #8
Text #9
Max Range: 7.3892. Min Range: -7.3892
Max Act: 6.8892. Min Act: -0.1700
Data Index: 974174 (Open Web Text)
Max Activating Token Index: 767
Click toggle to see full text
Truncated
Full Text #9
Text #10
Max Range: 7.3892. Min Range: -7.3892
Max Act: 6.8892. Min Act: -0.1700
Data Index: 3855649 (Open Web Text)
Max Activating Token Index: 356
Click toggle to see full text
Truncated
Full Text #10
Text #11
Max Range: 7.3892. Min Range: -7.3892
Max Act: 6.8579. Min Act: -0.1700
Data Index: 148198 (Open Web Text)
Max Activating Token Index: 773
Click toggle to see full text
Truncated
Full Text #11
Text #12
Max Range: 7.3892. Min Range: -7.3892
Max Act: 6.8579. Min Act: -0.1700
Data Index: 2803696 (Open Web Text)
Max Activating Token Index: 560
Click toggle to see full text
Truncated
Full Text #12
Text #13
Max Range: 7.3892. Min Range: -7.3892
Max Act: 6.8579. Min Act: -0.1700
Data Index: 5271062 (Open Web Text)
Max Activating Token Index: 121
Click toggle to see full text
Truncated
Full Text #13
Text #14
Max Range: 7.3892. Min Range: -7.3892
Max Act: 6.8579. Min Act: -0.1700
Data Index: 3443819 (Open Web Text)
Max Activating Token Index: 225
Click toggle to see full text
Truncated
Full Text #14
Text #15
Max Range: 7.3892. Min Range: -7.3892
Max Act: 6.8579. Min Act: -0.1700
Data Index: 6483143 (Open Web Text)
Max Activating Token Index: 572
Click toggle to see full text
Truncated
Full Text #15
Text #16
Max Range: 7.3892. Min Range: -7.3892
Max Act: 6.8579. Min Act: -0.1700
Data Index: 6439855 (Open Web Text)
Max Activating Token Index: 534
Click toggle to see full text
Truncated
Full Text #16
Text #17
Max Range: 7.3892. Min Range: -7.3892
Max Act: 6.8579. Min Act: -0.1700
Data Index: 1196314 (Open Web Text)
Max Activating Token Index: 486
Click toggle to see full text
Truncated
Full Text #17
Text #18
Max Range: 7.3892. Min Range: -7.3892
Max Act: 6.8892. Min Act: -0.1700
Data Index: 6044752 (Open Web Text)
Max Activating Token Index: 683
Click toggle to see full text
Truncated
Full Text #18
Text #19
Max Range: 7.3892. Min Range: -7.3892
Max Act: 6.7954. Min Act: -0.1700
Data Index: 4879377 (Open Web Text)
Max Activating Token Index: 800
Click toggle to see full text
Truncated
Full Text #19